Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2411 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 12236 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 37449 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 18256 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 78409 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 62861 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 61896 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 14573 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 59460 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 908 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 12257 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 38330 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 23444 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 55371 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 3370 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 22835 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 54752 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 53107 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 46263 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0002
Data Index: 43756 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0418. Min Range: -0.0418
Max Act: 0.0418. Min Act: -0.0001
Data Index: 9125 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19